Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.11640 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912963125837824 |
|---|---|
| author | Qin, Sizhong Weber, Ramon Elias Lu, Xinzheng |
| author_facet | Qin, Sizhong Weber, Ramon Elias Lu, Xinzheng |
| contents | Architectural floor plan design demands joint reasoning over geometry, semantics, and spatial hierarchy, which remains a major challenge for current AI systems. Although recent diffusion and language models improve visual fidelity, they still struggle with coherent spatial reasoning and controllable generation. We present HouseMind, a multimodal large language model that unifies floor plan understanding, generation, and editing in one framework. We introduce discrete room-instance tokens to construct a unified vocabulary that bridges layouts and symbolic reasoning. With multimodal alignment and instruction tuning, the model synthesizes coherent, controllable layouts from text instructions. Experiments show how the framework achieves superior geometric validity and controllability while remaining efficient and locally deployable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_11640 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans Qin, Sizhong Weber, Ramon Elias Lu, Xinzheng Computer Vision and Pattern Recognition Artificial Intelligence Architectural floor plan design demands joint reasoning over geometry, semantics, and spatial hierarchy, which remains a major challenge for current AI systems. Although recent diffusion and language models improve visual fidelity, they still struggle with coherent spatial reasoning and controllable generation. We present HouseMind, a multimodal large language model that unifies floor plan understanding, generation, and editing in one framework. We introduce discrete room-instance tokens to construct a unified vocabulary that bridges layouts and symbolic reasoning. With multimodal alignment and instruction tuning, the model synthesizes coherent, controllable layouts from text instructions. Experiments show how the framework achieves superior geometric validity and controllability while remaining efficient and locally deployable. |
| title | Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.11640 |